An Evaluation Framework and Database for MoCap-Based Gait
Recognition Methods

D 2017

An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods

BALÁŽIA, Michal a Petr SOJKA

Základní údaje

Originální název

An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods

Autoři

BALÁŽIA, Michal (703 Slovensko, garant, domácí) a Petr SOJKA (203 Česká republika, domácí)

Vydání

LNCS 10214. Switzerland, Proceedings of the 1st IAPR Workshop on Reproducible Research in Pattern Recognition (RRPR 2016), od s. 33-47, 15 s. 2017

Nakladatel

Springer International Publishing AG

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Švýcarsko

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

tištěná verze "print"

Odkazy

DOI conference web arXiv preprint

Impakt faktor

Impact factor: 0.402 v roce 2005

Kód RIV

RIV/00216224:14330/17:00095907

Organizační jednotka

Fakulta informatiky

ISBN

978-3-319-56413-5

ISSN

DOI

http://dx.doi.org/10.1007/978-3-319-56414-2_3

UT WoS

000426089600003

Klíčová slova česky

softwarový evaluační framework; databáze dvoukroků; rozpoznávání lidi podle chůze

Klíčová slova anglicky

software evaluation framework; gait cycle database; human gait recognition

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 18. 5. 2018 12:20, RNDr. Pavel Šmerk, Ph.D.

Anotace

V originále

As a contribution to reproducible research, this paper presents a framework and a database to improve the development, evaluation and comparison of methods for gait recognition from Motion Capture (MoCap) data. The evaluation framework provides implementation details and source codes of state-of-the-art human-interpretable geometric features as well as our own approaches where gait features are learned by a modification of Fisher's Linear Discriminant Analysis with the Maximum Margin Criterion, and by a combination of Principal Component Analysis and Linear Discriminant Analysis. It includes a description and source codes of a mechanism for evaluating four class separability coefficients of feature space and four rank-based classifier performance metrics. This framework also contains a tool for learning a custom classifier and for classifying a custom query on a custom gallery. We provide an experimental database along with source codes for its extraction from the general CMU MoCap database.

Návaznosti

MUNI/A/0892/2015, interní kód MU

Název: Výzkum v aplikované informatice na FI MU (Akronym: VAIFIMU)

Investor: Masarykova univerzita, Výzkum v aplikované informatice na FI MU, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

MUNI/A/0935/2015, interní kód MU

Název: Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity (Akronym: SKOMU)

Investor: Masarykova univerzita, Zapojení studentů Fakulty informatiky do mezinárodní vědecké komunity, DO R. 2020_Kategorie A - Specifický výzkum - Studentské výzkumné projekty

Přiložené soubory

rrpr2arxiv.pdf

Vyhledat podobné dokumenty

Citovat

BALÁŽIA, Michal a Petr SOJKA. An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods. In Miguel Colom, Bertrand Kerautret and Pascal Monasse. Proceedings of the 1st IAPR Workshop on Reproducible Research in Pattern Recognition (RRPR 2016). LNCS 10214. Switzerland: Springer International Publishing AG, 2017, s. 33-47. ISBN 978-3-319-56413-5. Dostupné z: https://dx.doi.org/10.1007/978-3-319-56414-2_3.

@inproceedings{1359622,
   author = {Balážia, Michal and Sojka, Petr},
   address = {Switzerland},
   booktitle = {Proceedings of the 1st IAPR Workshop on Reproducible Research in Pattern Recognition (RRPR 2016)},
   doi = {http://dx.doi.org/10.1007/978-3-319-56414-2_3},
   edition = {LNCS 10214},
   editor = {Miguel Colom, Bertrand Kerautret and Pascal Monasse},
   keywords = {software evaluation framework; gait cycle database; human gait recognition},
   howpublished = {tištěná verze "print"},
   language = {eng},
   location = {Switzerland},
   isbn = {978-3-319-56413-5},
   pages = {33-47},
   publisher = {Springer International Publishing AG},
   title = {An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods},
   url = {https://doi.org/10.1007/978-3-319-56414-2_3},
   year = {2017}
}

TY  - JOUR
ID  - 1359622
AU  - Balážia, Michal - Sojka, Petr
PY  - 2017
TI  - An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods
PB  - Springer International Publishing AG
CY  - Switzerland
SN  - 9783319564135
KW  - software evaluation framework
KW  - gait cycle database
KW  - human gait recognition
UR  - https://doi.org/10.1007/978-3-319-56414-2_3
L2  - https://doi.org/10.1007/978-3-319-56414-2_3
N2  - As a contribution to reproducible research, this paper presents a framework and a database to improve the development, evaluation and comparison of methods for gait recognition from Motion Capture (MoCap) data. The evaluation framework provides implementation details and source codes of state-of-the-art human-interpretable geometric features as well as our own approaches where gait features are learned by a modification of Fisher's Linear Discriminant Analysis with the Maximum Margin Criterion, and by a combination of Principal Component Analysis and Linear Discriminant Analysis. It includes a description and source codes of a mechanism for evaluating four class separability coefficients of feature space and four rank-based classifier performance metrics. This framework also contains a tool for learning a custom classifier and for classifying a custom query on a custom gallery. We provide an experimental database along with source codes for its extraction from the general CMU MoCap database.
ER  -

BALÁŽIA, Michal a Petr SOJKA. An Evaluation Framework and Database for MoCap-Based Gait Recognition Methods. In Miguel Colom, Bertrand Kerautret and Pascal Monasse. \textit{Proceedings of the 1st IAPR Workshop on Reproducible Research in Pattern Recognition (RRPR 2016)}. LNCS 10214. Switzerland: Springer International Publishing AG, 2017, s.~33-47. ISBN~978-3-319-56413-5. Dostupné z: https://dx.doi.org/10.1007/978-3-319-56414-2\_{}3.

Podrobný výpis o publikaci